lewtun's picture
lewtun HF staff
Upload eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/main/lcb/results_2025-02-22T16-28-24.361122.json with huggingface_hub
edf2f0e verified
raw
history blame
2.62 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": -1,
"max_samples": null,
"job_id": 0,
"start_time": 74724.675363062,
"end_time": 97661.659397967,
"total_evaluation_time_secondes": "22936.984034905006",
"model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"model_sha": "",
"model_dtype": null,
"model_size": null
},
"results": {
"extended|lcb:codegeneration|0": {
"codegen_pass@1:16": 0.5163246268656716,
"codegen_pass@1:16_stderr": 0.026503774649630295
},
"all": {
"codegen_pass@1:16": 0.5163246268656716,
"codegen_pass@1:16_stderr": 0.026503774649630295
}
},
"versions": {
"extended|lcb:codegeneration|0": 0
},
"config_tasks": {
"extended|lcb:codegeneration": {
"name": "lcb:codegeneration",
"prompt_function": "lcb_codegeneration_prompt_fn",
"hf_repo": "livecodebench/code_generation_lite",
"hf_subset": "v4_v5",
"metric": [
{
"metric_name": "codegen_pass@1:16",
"higher_is_better": true,
"category": "5",
"use_case": "6",
"sample_level_fn": "codegen_metric",
"corpus_level_fn": "mean"
}
],
"hf_revision": null,
"hf_filter": null,
"hf_avail_splits": [
"test"
],
"trust_dataset": true,
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 32768,
"generation_grammar": null,
"stop_sequence": [],
"num_samples": null,
"suite": [
"extended"
],
"original_num_docs": 268,
"effective_num_docs": 268,
"must_remove_duplicate_docs": false,
"version": 0
}
},
"summary_tasks": {
"extended|lcb:codegeneration|0": {
"hashes": {
"hash_examples": "ecc02ff275410b52",
"hash_full_prompts": "54c79c85387f79eb",
"hash_input_tokens": "c9b3c5ec91511267",
"hash_cont_tokens": "5254187716b4e916"
},
"truncated": 0,
"non_truncated": 268,
"padded": 0,
"non_padded": 268,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "f850b9be453f7d4f",
"hash_full_prompts": "51901899cfc8030e",
"hash_input_tokens": "dd5902dd810391e1",
"hash_cont_tokens": "f62c6e91e3d31234"
},
"truncated": 0,
"non_truncated": 268,
"padded": 0,
"non_padded": 268,
"num_truncated_few_shots": 0
}
}